rirv938-gy-grpo-cp312-9_54074

developer_uid: rirv938

submission_id: rirv938-gy-grpo-cp312-9_54074_v1

model_name: rirv938-gy-grpo-cp312-9_54074_v1

model_group: rirv938/gy_grpo_cp312_98

status: torndown

timestamp: 2025-07-03T04:13:01+00:00

num_battles: 6652

num_wins: 3496

celo_rating: 1304.51

family_friendly_score: 0.4958

family_friendly_standard_error: 0.007070818340192315

submission_type: basic

model_repo: rirv938/gy_grpo_cp312_98ff_b35_r1_merged

model_architecture: MistralForCausalLM

model_num_parameters: 24096691200.0

best_of: 8

max_input_tokens: 768

max_output_tokens: 64

reward_model: default

latencies: [{'batch_size': 1, 'throughput': 0.5400789039550825, 'latency_mean': 1.8514767813682556, 'latency_p50': 1.8634934425354004, 'latency_p90': 2.0419268369674684}, {'batch_size': 3, 'throughput': 1.1317625873423176, 'latency_mean': 2.645331639051437, 'latency_p50': 2.6285958290100098, 'latency_p90': 2.945033597946167}, {'batch_size': 5, 'throughput': 1.436263301681963, 'latency_mean': 3.4454160499572755, 'latency_p50': 3.4832507371902466, 'latency_p90': 3.8574515104293825}, {'batch_size': 6, 'throughput': 1.5869137578157806, 'latency_mean': 3.7477198636531828, 'latency_p50': 3.7015178203582764, 'latency_p90': 4.23784441947937}, {'batch_size': 8, 'throughput': 1.7630259231082048, 'latency_mean': 4.498618553876877, 'latency_p50': 4.504103302955627, 'latency_p90': 5.046126842498779}, {'batch_size': 10, 'throughput': 1.8380643374009962, 'latency_mean': 5.3712921977043155, 'latency_p50': 5.408012509346008, 'latency_p90': 6.015283370018005}]

gpu_counts: {'NVIDIA A100-SXM4-80GB': 1}

display_name: rirv938-gy-grpo-cp312-9_54074_v1

is_internal_developer: True

language_model: rirv938/gy_grpo_cp312_98ff_b35_r1_merged

model_size: 24B

ranking_group: single

throughput_3p7s: 1.58

us_pacific_date: 2025-07-02

win_ratio: 0.5255562236921226

generation_params: {'temperature': 1.0, 'top_p': 0.95, 'min_p': 0.05, 'top_k': 80, 'presence_penalty': 0.45, 'frequency_penalty': 0.45, 'stopping_words': ['###', '\n', 'You:', '</s>'], 'max_input_tokens': 768, 'best_of': 8, 'max_output_tokens': 64}

formatter: {'memory_template': '', 'prompt_template': '', 'bot_template': '{bot_name}: {message}\n', 'user_template': '{user_name}: {message}\n', 'response_template': '{bot_name}:', 'truncate_by_message': False}

Resubmit model

Shutdown handler not registered because Python interpreter is not running in the main thread
run pipeline %s
run pipeline stage %s
Running pipeline stage MKMLizer
Starting job with name rirv938-gy-grpo-cp312-9-54074-v1-mkmlizer
Waiting for job on rirv938-gy-grpo-cp312-9-54074-v1-mkmlizer to finish
rirv938-gy-grpo-cp312-9-54074-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
rirv938-gy-grpo-cp312-9-54074-v1-mkmlizer: ║                                                                     ║
rirv938-gy-grpo-cp312-9-54074-v1-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
rirv938-gy-grpo-cp312-9-54074-v1-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
rirv938-gy-grpo-cp312-9-54074-v1-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
rirv938-gy-grpo-cp312-9-54074-v1-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
rirv938-gy-grpo-cp312-9-54074-v1-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
rirv938-gy-grpo-cp312-9-54074-v1-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
rirv938-gy-grpo-cp312-9-54074-v1-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
rirv938-gy-grpo-cp312-9-54074-v1-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
rirv938-gy-grpo-cp312-9-54074-v1-mkmlizer: ║                                                                     ║
rirv938-gy-grpo-cp312-9-54074-v1-mkmlizer: ║  Version: 0.29.15                                                   ║
rirv938-gy-grpo-cp312-9-54074-v1-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
rirv938-gy-grpo-cp312-9-54074-v1-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
rirv938-gy-grpo-cp312-9-54074-v1-mkmlizer: ║  https://mk1.ai                                                     ║
rirv938-gy-grpo-cp312-9-54074-v1-mkmlizer: ║                                                                     ║
rirv938-gy-grpo-cp312-9-54074-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
rirv938-gy-grpo-cp312-9-54074-v1-mkmlizer: ║  belonging to:                                                      ║
rirv938-gy-grpo-cp312-9-54074-v1-mkmlizer: ║                                                                     ║
rirv938-gy-grpo-cp312-9-54074-v1-mkmlizer: ║  Chai Research Corp.                                                ║
rirv938-gy-grpo-cp312-9-54074-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
rirv938-gy-grpo-cp312-9-54074-v1-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
rirv938-gy-grpo-cp312-9-54074-v1-mkmlizer: ║                                                                     ║
rirv938-gy-grpo-cp312-9-54074-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
Failed to get response for submission chaiml-qwen3-8breranker_67576_v2: HTTPConnectionPool(host='chaiml-qwen3-8breranker-67576-v2-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
rirv938-gy-grpo-cp312-9-54074-v1-mkmlizer: Downloaded to shared memory in 158.022s
rirv938-gy-grpo-cp312-9-54074-v1-mkmlizer: Checking if rirv938/gy_grpo_cp312_98ff_b35_r1_merged already exists in ChaiML
rirv938-gy-grpo-cp312-9-54074-v1-mkmlizer: Creating repo ChaiML/gy_grpo_cp312_98ff_b35_r1_merged and uploading /tmp/tmpv416lq20 to it
Failed to get response for submission chaiml-qwen3-8breranker_67576_v2: HTTPConnectionPool(host='chaiml-qwen3-8breranker-67576-v2-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
rirv938-gy-grpo-cp312-9-54074-v1-mkmlizer: 
  0%|          | 0/22 [00:00<?, ?it/s]
  5%|▍         | 1/22 [00:05<01:51,  5.32s/it]
  9%|▉         | 2/22 [00:08<01:25,  4.30s/it]
 14%|█▎        | 3/22 [00:14<01:32,  4.86s/it]
 18%|█▊        | 4/22 [00:18<01:21,  4.53s/it]
 23%|██▎       | 5/22 [00:22<01:11,  4.18s/it]
 27%|██▋       | 6/22 [00:25<01:02,  3.91s/it]
 32%|███▏      | 7/22 [00:33<01:19,  5.30s/it]
 36%|███▋      | 8/22 [00:41<01:27,  6.25s/it]
 41%|████      | 9/22 [00:47<01:20,  6.20s/it]
 45%|████▌     | 10/22 [00:53<01:12,  6.03s/it]
 50%|█████     | 11/22 [00:57<00:59,  5.38s/it]
 55%|█████▍    | 12/22 [01:00<00:47,  4.77s/it]
 59%|█████▉    | 13/22 [01:07<00:48,  5.39s/it]
 64%|██████▎   | 14/22 [01:14<00:46,  5.80s/it]
 68%|██████▊   | 15/22 [01:20<00:41,  5.89s/it]
 73%|███████▎  | 16/22 [01:24<00:31,  5.19s/it]
 77%|███████▋  | 17/22 [01:32<00:30,  6.09s/it]
 82%|████████▏ | 18/22 [01:35<00:21,  5.38s/it]
 86%|████████▋ | 19/22 [01:39<00:14,  4.77s/it]
 91%|█████████ | 20/22 [01:45<00:10,  5.25s/it]
 95%|█████████▌| 21/22 [01:50<00:05,  5.16s/it]
100%|██████████| 22/22 [01:51<00:00,  3.95s/it]
100%|██████████| 22/22 [01:51<00:00,  5.08s/it]
rirv938-gy-grpo-cp312-9-54074-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpv416lq20, device:0
rirv938-gy-grpo-cp312-9-54074-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
rirv938-gy-grpo-cp312-9-54074-v1-mkmlizer: quantized model in 55.983s
rirv938-gy-grpo-cp312-9-54074-v1-mkmlizer: Processed model rirv938/gy_grpo_cp312_98ff_b35_r1_merged in 417.987s
rirv938-gy-grpo-cp312-9-54074-v1-mkmlizer: creating bucket guanaco-mkml-models
rirv938-gy-grpo-cp312-9-54074-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
rirv938-gy-grpo-cp312-9-54074-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/rirv938-gy-grpo-cp312-9-54074-v1/nvidia
rirv938-gy-grpo-cp312-9-54074-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/rirv938-gy-grpo-cp312-9-54074-v1/nvidia/special_tokens_map.json
rirv938-gy-grpo-cp312-9-54074-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/rirv938-gy-grpo-cp312-9-54074-v1/nvidia/config.json
rirv938-gy-grpo-cp312-9-54074-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/rirv938-gy-grpo-cp312-9-54074-v1/nvidia/tokenizer_config.json
rirv938-gy-grpo-cp312-9-54074-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/rirv938-gy-grpo-cp312-9-54074-v1/nvidia/tokenizer.json
rirv938-gy-grpo-cp312-9-54074-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/rirv938-gy-grpo-cp312-9-54074-v1/nvidia/flywheel_model.1.safetensors
rirv938-gy-grpo-cp312-9-54074-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/rirv938-gy-grpo-cp312-9-54074-v1/nvidia/flywheel_model.0.safetensors
rirv938-gy-grpo-cp312-9-54074-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 3/363 [00:00<00:12, 29.74it/s]
Loading 0:   2%|▏         | 6/363 [00:00<00:24, 14.54it/s]
Loading 0:   3%|▎         | 11/363 [00:00<00:16, 21.99it/s]
Loading 0:   4%|▍         | 14/363 [00:00<00:25, 13.58it/s]
Loading 0:   4%|▍         | 16/363 [00:01<00:26, 13.33it/s]
Loading 0:   6%|▌         | 21/363 [00:01<00:20, 17.00it/s]
Loading 0:   6%|▋         | 23/363 [00:01<00:24, 13.75it/s]
Loading 0:   8%|▊         | 28/363 [00:01<00:17, 19.56it/s]
Loading 0:   9%|▉         | 32/363 [00:01<00:14, 23.10it/s]
Loading 0:  10%|▉         | 35/363 [00:02<00:21, 15.29it/s]
Loading 0:  10%|█         | 38/363 [00:02<00:19, 16.25it/s]
Loading 0:  11%|█▏        | 41/363 [00:02<00:24, 12.95it/s]
Loading 0:  13%|█▎        | 46/363 [00:02<00:17, 18.27it/s]
Loading 0:  14%|█▍        | 50/363 [00:02<00:14, 21.79it/s]
Loading 0:  15%|█▍        | 54/363 [00:03<00:22, 13.95it/s]
Loading 0:  16%|█▌        | 57/363 [00:03<00:19, 15.94it/s]
Loading 0:  17%|█▋        | 60/363 [00:03<00:20, 14.61it/s]
Loading 0:  18%|█▊        | 64/363 [00:03<00:16, 18.28it/s]
Loading 0:  19%|█▊        | 68/363 [00:03<00:13, 21.90it/s]
Loading 0:  20%|█▉        | 71/363 [00:04<00:18, 15.41it/s]
Loading 0:  20%|██        | 74/363 [00:04<00:17, 16.22it/s]
Loading 0:  21%|██        | 77/363 [00:04<00:22, 12.84it/s]
Loading 0:  23%|██▎       | 82/363 [00:04<00:15, 18.05it/s]
Loading 0:  24%|██▎       | 86/363 [00:05<00:12, 21.52it/s]
Loading 0:  25%|██▍       | 89/363 [00:05<00:17, 15.47it/s]
Loading 0:  25%|██▌       | 92/363 [00:05<00:17, 15.93it/s]
Loading 0:  26%|██▋       | 96/363 [00:05<00:13, 19.81it/s]
Loading 0:  28%|██▊       | 101/363 [00:05<00:12, 21.80it/s]
Loading 0:  29%|██▊       | 104/363 [00:06<00:14, 18.31it/s]
Loading 0:  29%|██▉       | 107/363 [00:06<00:18, 14.06it/s]
Loading 0:  30%|███       | 109/363 [00:06<00:18, 13.83it/s]
Loading 0:  31%|███       | 111/363 [00:06<00:17, 14.65it/s]
Loading 0:  31%|███       | 113/363 [00:06<00:20, 12.33it/s]
Loading 0:  33%|███▎      | 118/363 [00:07<00:13, 18.78it/s]
Loading 0:  34%|███▎      | 122/363 [00:07<00:10, 22.82it/s]
Loading 0:  34%|███▍      | 125/363 [00:07<00:14, 15.87it/s]
Loading 0:  35%|███▌      | 128/363 [00:07<00:14, 16.77it/s]
Loading 0:  36%|███▌      | 131/363 [00:08<00:17, 13.31it/s]
Loading 0:  37%|███▋      | 136/363 [00:08<00:12, 18.77it/s]
Loading 0:  39%|███▊      | 140/363 [00:08<00:09, 22.40it/s]
Loading 0:  40%|███▉      | 144/363 [00:08<00:15, 14.47it/s]
Loading 0:  40%|████      | 147/363 [00:08<00:13, 16.33it/s]
Loading 0:  41%|████▏     | 150/363 [00:09<00:14, 15.02it/s]
Loading 0:  42%|████▏     | 154/363 [00:09<00:11, 18.80it/s]
Loading 0:  44%|████▎     | 158/363 [00:09<00:09, 22.16it/s]
Loading 0:  44%|████▍     | 161/363 [00:09<00:12, 15.84it/s]
Loading 0:  45%|████▌     | 164/363 [00:09<00:11, 16.60it/s]
Loading 0:  46%|████▌     | 167/363 [00:10<00:14, 13.08it/s]
Loading 0:  47%|████▋     | 172/363 [00:10<00:10, 18.23it/s]
Loading 0:  48%|████▊     | 176/363 [00:10<00:08, 21.03it/s]
Loading 0:  49%|████▉     | 179/363 [00:10<00:12, 15.13it/s]
Loading 0:  50%|█████     | 182/363 [00:10<00:11, 15.94it/s]
Loading 0:  51%|█████     | 185/363 [00:11<00:14, 12.59it/s]
Loading 0:  52%|█████▏    | 190/363 [00:11<00:09, 17.68it/s]
Loading 0:  53%|█████▎    | 194/363 [00:11<00:07, 21.29it/s]
Loading 0:  54%|█████▍    | 197/363 [00:11<00:10, 15.48it/s]
Loading 0:  55%|█████▌    | 200/363 [00:12<00:09, 16.34it/s]
Loading 0:  56%|█████▌    | 203/363 [00:26<03:40,  1.38s/it]
Loading 0:  57%|█████▋    | 207/363 [00:26<02:22,  1.09it/s]
Loading 0:  58%|█████▊    | 210/363 [00:26<01:44,  1.47it/s]
Loading 0:  59%|█████▊    | 213/363 [00:27<01:17,  1.94it/s]
Loading 0:  60%|█████▉    | 216/363 [00:27<00:59,  2.49it/s]
Loading 0:  60%|██████    | 219/363 [00:27<00:42,  3.38it/s]
Loading 0:  61%|██████    | 222/363 [00:27<00:32,  4.28it/s]
Loading 0:  62%|██████▏   | 226/363 [00:27<00:21,  6.24it/s]
Loading 0:  63%|██████▎   | 230/363 [00:28<00:15,  8.70it/s]
Loading 0:  64%|██████▍   | 233/363 [00:28<00:15,  8.63it/s]
Loading 0:  65%|██████▌   | 236/363 [00:28<00:12, 10.22it/s]
Loading 0:  66%|██████▌   | 239/363 [00:28<00:12,  9.69it/s]
Loading 0:  67%|██████▋   | 244/363 [00:28<00:08, 14.30it/s]
Loading 0:  68%|██████▊   | 248/363 [00:29<00:06, 17.80it/s]
Loading 0:  69%|██████▉   | 252/363 [00:29<00:08, 12.78it/s]
Loading 0:  70%|███████   | 255/363 [00:29<00:07, 14.83it/s]
Loading 0:  71%|███████   | 258/363 [00:29<00:07, 14.09it/s]
Loading 0:  72%|███████▏  | 262/363 [00:30<00:05, 17.75it/s]
Loading 0:  73%|███████▎  | 266/363 [00:30<00:04, 21.42it/s]
Loading 0:  74%|███████▍  | 269/363 [00:30<00:06, 15.39it/s]
Loading 0:  75%|███████▍  | 272/363 [00:30<00:05, 16.20it/s]
Loading 0:  76%|███████▌  | 275/363 [00:31<00:06, 12.92it/s]
Loading 0:  77%|███████▋  | 280/363 [00:31<00:04, 17.72it/s]
Loading 0:  78%|███████▊  | 284/363 [00:31<00:03, 20.58it/s]
Loading 0:  79%|███████▉  | 287/363 [00:31<00:05, 14.95it/s]
Loading 0:  80%|███████▉  | 290/363 [00:31<00:04, 15.87it/s]
Loading 0:  81%|████████  | 293/363 [00:32<00:05, 12.87it/s]
Loading 0:  82%|████████▏ | 298/363 [00:32<00:03, 18.01it/s]
Loading 0:  83%|████████▎ | 302/363 [00:32<00:02, 21.52it/s]
Loading 0:  84%|████████▍ | 305/363 [00:32<00:03, 15.82it/s]
Loading 0:  85%|████████▍ | 308/363 [00:32<00:03, 16.65it/s]
Loading 0:  86%|████████▌ | 311/363 [00:33<00:03, 13.35it/s]
Loading 0:  87%|████████▋ | 316/363 [00:33<00:02, 18.61it/s]
Loading 0:  88%|████████▊ | 320/363 [00:33<00:01, 22.16it/s]
Loading 0:  89%|████████▉ | 324/363 [00:33<00:02, 14.52it/s]
Loading 0:  90%|█████████ | 327/363 [00:33<00:02, 16.61it/s]
Loading 0:  91%|█████████ | 330/363 [00:34<00:02, 15.23it/s]
Loading 0:  92%|█████████▏| 334/363 [00:34<00:01, 19.08it/s]
Loading 0:  93%|█████████▎| 338/363 [00:34<00:01, 22.72it/s]
Loading 0:  94%|█████████▍| 342/363 [00:34<00:01, 14.48it/s]
Loading 0:  95%|█████████▌| 345/363 [00:35<00:01, 16.59it/s]
Loading 0:  96%|█████████▌| 348/363 [00:35<00:00, 15.13it/s]
Loading 0:  97%|█████████▋| 352/363 [00:35<00:00, 19.04it/s]
Loading 0:  98%|█████████▊| 356/363 [00:35<00:00, 22.72it/s]
Loading 0:  99%|█████████▉| 360/363 [00:36<00:00, 11.75it/s]
Loading 0: 100%|██████████| 363/363 [00:36<00:00, 13.07it/s]
                                                            
Job rirv938-gy-grpo-cp312-9-54074-v1-mkmlizer completed after 505.79s with status: succeeded
Stopping job with name rirv938-gy-grpo-cp312-9-54074-v1-mkmlizer
Pipeline stage MKMLizer completed in 506.26s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.14s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service rirv938-gy-grpo-cp312-9-54074-v1
Waiting for inference service rirv938-gy-grpo-cp312-9-54074-v1 to be ready
Inference service rirv938-gy-grpo-cp312-9-54074-v1 ready after 210.7659924030304s
Pipeline stage MKMLDeployer completed in 211.39s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.626446485519409s
Received healthy response to inference request in 2.185453414916992s
Received healthy response to inference request in 1.8255505561828613s
Received healthy response to inference request in 1.6923730373382568s
Received healthy response to inference request in 2.004810333251953s
5 requests
0 failed requests
5th percentile: 1.7190085411071778
10th percentile: 1.7456440448760986
20th percentile: 1.7989150524139403
30th percentile: 1.8614025115966797
40th percentile: 1.9331064224243164
50th percentile: 2.004810333251953
60th percentile: 2.077067565917969
70th percentile: 2.1493247985839843
80th percentile: 2.2736520290374758
90th percentile: 2.4500492572784425
95th percentile: 2.5382478713989256
99th percentile: 2.6088067626953126
mean time: 2.0669267654418944
Pipeline stage StressChecker completed in 11.79s
run pipeline stage %s
Running pipeline stage OfflineFamilyFriendlyTriggerPipeline
run_pipeline:run_in_cloud %s
starting trigger_guanaco_pipeline args=%s
triggered trigger_guanaco_pipeline args=%s
Pipeline stage OfflineFamilyFriendlyTriggerPipeline completed in 0.65s
run pipeline stage %s
Running pipeline stage TriggerMKMLProfilingPipeline
run_pipeline:run_in_cloud %s
starting trigger_guanaco_pipeline args=%s
triggered trigger_guanaco_pipeline args=%s
Pipeline stage TriggerMKMLProfilingPipeline completed in 0.61s
Shutdown handler de-registered
rirv938-gy-grpo-cp312-9_54074_v1 status is now deployed due to DeploymentManager action
Shutdown handler registered
run pipeline %s
run pipeline stage %s
Shutdown handler registered
run pipeline %s
run pipeline stage %s
Running pipeline stage OfflineFamilyFriendlyScorer
Evaluating %s Family Friendly Score with %s threads
Pipeline stage OfflineFamilyFriendlyScorer completed in 3071.61s
Shutdown handler de-registered
rirv938-gy-grpo-cp312-9_54074_v1 status is now inactive due to auto deactivation removed underperforming models
rirv938-gy-grpo-cp312-9_54074_v1 status is now torndown due to DeploymentManager action